Download

Get Belltongue

Free for 14 days, every feature included. No card needed.

Belltongue 1.0 for Mac

macOS 14 Sonoma or later · Apple silicon (M1 or later)

By installing Belltongue you agree to the License Agreement. What’s new

macOS 14 Sonoma or later

Apple silicon (M1 or later). Intel Macs aren’t supported.

Once, to download the speech models. After that, recognition works offline.

Belltongue walks you through all of this when it first opens. It takes about two minutes.

Install
Open the downloaded .dmg and drag Belltongue to Applications. Open it from Applications — it lives in the menu bar.
Allow Microphone and Accessibility
Microphone, to hear you while you dictate. Accessibility, to notice the fn key, find your cursor and type the text there. macOS may also ask about other apps’ audio: Belltongue only uses that to quiet music and videos while you talk, and never records it.
Download the speech models
A one-time download from the models’ publishers: about 160 MB for Chinese and English, plus about 630 MB if you add the recommended English model. Then recognition runs entirely on your Mac.
Choose AI cleanup — or not
Sign in with OpenRouter to use free models, paste your own API key, or skip it and get the on-device transcript as is. You can change this anytime in Settings.
Free up the fn key
In System Settings › Keyboard, set “Press 🌐 key to” to “Do Nothing”, so fn doesn’t also open emoji or Apple’s dictation.
Press fn and talk
Click into any text field, press fn, speak, press fn again. That’s it.

Stuck? Email [email protected] — a real person answers.